{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/probabilistic-binary-neural-networks","title":"Probabilistic Binary Neural Networks","arxiv_id":"1809.03368","date":"2018-09-10","proceeding":"ICLR 2019 5","authors":["Jorn W. T. Peters","Max Welling"],"abstract":"Low bit-width weights and activations are an effective way of combating the\nincreasing need for both memory and compute power of Deep Neural Networks. In\nthis work, we present a probabilistic training method for Neural Network with\nboth binary weights and activations, called BLRNet. By embracing stochasticity\nduring training, we circumvent the need to approximate the gradient of\nnon-differentiable functions such as sign(), while still obtaining a fully\nBinary Neural Network at test time. Moreover, it allows for anytime ensemble\npredictions for improved performance and uncertainty estimates by sampling from\nthe weight distribution. Since all operations in a layer of the BLRNet operate\non random variables, we introduce stochastic versions of Batch Normalization\nand max pooling, which transfer well to a deterministic network at test time.\nWe evaluate the BLRNet on multiple standardized benchmarks.","url_abs":"http://arxiv.org/abs/1809.03368v1","url_pdf":"http://arxiv.org/pdf/1809.03368v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"probabilistic-binary-neural-networks","repo_url":"https://github.com/COMP6248-Reproducability-Challenge/Reproduction-of-Probabilistic-binary-neural-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.03368","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}